A Bidirectional Tree Tagging Scheme for Joint Medical Relation Extraction

Joint extraction refers to extracting triples, composed of entities and relations, simultaneously from the text with a single model, but the existing methods rarely work well on sentences with overlapping issue, i.e., the same entity is included in multiple triples. In this paper, we propose a novel Bidirectional Tree Tagging (BiTT) scheme to label overlapping triples in the text. In a sentence, the triples with the same relation category are especially represented as two binary trees, each of which is converted into a word-level tags sequence to label each word. Based on our BiTT scheme, we develop an end-to-end classification framework to predict the BiTT tags. We adopt the Bi-LSTM layers and a pre-trained BERT encoder respectively as its encoder module, and obtain promising results in a public English dataset as well as a Chinese one. The source code is publicly available at https://anonymous/for/review.